Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3954
    Prev
    Next
    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -1.00
    ValueStyle
    -0.88
    enumi
    -0.84
     الحره
    -0.82
     Exactly
    -0.81
     بيها
    -0.79
    DoubleQuotes
    -0.78
    httphttps
    -0.77
    setVerticalGroup
    -0.74
     Need
    -0.71
    POSITIVE LOGITS
     conditional
    0.35
    aile
    0.34
    ahora
    0.33
    Regs
    0.33
    =−
    0.32
    cierge
    0.32
     suppressor
    0.32
     deletes
    0.31
    loroethene
    0.31
     Pologne
    0.31
    Activations Density 0.006%

    No Known Activations